University of Surrey

Test tubes in the lab Research in the ATI Dance Research

An Extended Algorithm Using Adaptation of Momentum and Learning Rate for Spiking Neurons Emitting Multiple Spikes

Luo, Yuling, Fu, Qiang, Liu, Junxiu, Harkin, Jim, McDaid, Liam and Cao, Yi (2017) An Extended Algorithm Using Adaptation of Momentum and Learning Rate for Spiking Neurons Emitting Multiple Spikes In: 14th International Work-Conference on Artificial Neural Networks (IWANN 2017), 14-16 Jun 2017, Cadiz, Spain.

Full text not available from this repository.

Abstract

This paper presents two methods of using the dynamic momentum and learning rate adaption, to improve learning performance in spiking neural networks where neurons are modelled as spiking multiple times. The optimum value for the momentum factor is obtained from the mean square error with respect to the gradient of synaptic weights in the proposed algorithm. The delta-bar-delta rule is employed as the learning rate adaptation method. The XOR and Wisconsin breast cancer (WBC) classification tasks are used to validate the proposed algorithms. Results demonstrate no error and a minimal error of 0.08 are achieved for the XOR and WBC classification tasks respectively, which are better than the original Booij’s algorithm. The minimum number of epochs for XOR and Wisconsin breast cancer tasks are 35 and 26 respectively, which are also faster than the original Booij’s algorithm – i.e. 135 (for XOR) and 97 (for WBC). Compared with the original algorithm with static momentum and learning rate, the proposed dynamic algorithms can control the convergence rate and learning performance more effectively.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Arts and Social Sciences > Surrey Business School
Authors :
NameEmailORCID
Luo, YulingUNSPECIFIEDUNSPECIFIED
Fu, QiangUNSPECIFIEDUNSPECIFIED
Liu, JunxiuUNSPECIFIEDUNSPECIFIED
Harkin, JimUNSPECIFIEDUNSPECIFIED
McDaid, LiamUNSPECIFIEDUNSPECIFIED
Cao, Yiyc0006@surrey.ac.ukUNSPECIFIED
Date : 2017
Identification Number : 10.1007/978-3-319-59153-7_49
Copyright Disclaimer : © Springer International Publishing AG 2017
Uncontrolled Keywords : Spiking neural networks; Learning rate; Momentum; Self-adaptation
Additional Information : Part of the Lecture Notes in Computer Science book series (LNCS, volume 10305)
Depositing User : Clive Harris
Date Deposited : 20 Sep 2017 09:10
Last Modified : 20 Sep 2017 09:10
URI: http://epubs.surrey.ac.uk/id/eprint/842344

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800